# ReinforcementLearning.jl vs POMDPs.jl

**URL:** <https://discourse.julialang.org/t/reinforcementlearning-jl-vs-pomdps-jl/81355>\
**Category:** Machine Learning\
**Tags:** package\
**Created:** [May 20, 2022, 10:17am UTC](https://discourse.julialang.org/t/reinforcementlearning-jl-vs-pomdps-jl/81355 "2022-05-20T10:17:42Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![filchristou](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/filchristou/32/26760_2.png) [@filchristou](https://discourse.julialang.org/u/filchristou)\
**Post date:** [May 20, 2022, 10:17am UTC](https://discourse.julialang.org/t/reinforcementlearning-jl-vs-pomdps-jl/81355/1 "2022-05-20T10:17:42Z")

</div>

Hello. Some weeks ago, there was a live session regarding the ReinforcementLearning.jl package, and some of the questions were to identify differences, overlaps, and cooperation opportunities with the JuliaPOMDP organization.

[![](https://global.discourse-cdn.com/julialang/original/3X/a/4/a40fb99bb978a92efdb45e6521e4ed56a3e7d235.jpeg "ReinforcementLearning jl | Jun Tian | Julia User Group Munich - Share&Code") ](https://www.youtube.com/watch?v=ckIIxKM14Ow)

I did more attempts toward such an understanding in the past

> [@Reinforcement learning and e.g. deep kernel learning, and status of Julia for such AI](https://discourse.julialang.org/t/reinforcement-learning-and-e-g-deep-kernel-learning-and-status-of-julia-for-such-ai/63343/4):
>
> Hi nice overview. Certainly another Julia possiblity to consider would be all the [JuliaPOMDP](https://github.com/JuliaPOMDP) packages. The way I see it (and please correct me if I am wrong) this POMDPs packages together with the [ReinforcementLearning](https://juliareinforcementlearning.org/) packages are the ones gaining the most traction. (?) Of course I don’t want to undermine other packages which could be equally interesting for someone to investigate. While I am only just starting to investigate these packages I find it quite confusing to differentiate them. D…

[https://julialang.zulipchat.com/#narrow/stream/270794-reinforcement-learning/topic/ReinforcementLearning.2Ejl.20vs.20POMDPs.2Ejl](https://julialang.zulipchat.com/#narrow/stream/270794-reinforcement-learning/topic/ReinforcementLearning.2Ejl.20vs.20POMDPs.2Ejl)

I 've used both packages but in a very simplistic way, and I am always quite confused about what to pick for an application. Or maybe if both are appropriate and interplay nicely ?  
Moreover, regarding future developments would it make sense to coordinate future efforts on the field ?

It would be very nice if someone could offer their perspective on these, making an overview of these packages as a comparison to each other.

I took the liberty of mentioning some of the core developers of each organization.  
@findmyway @zsunberg  
I hope it’s fine 😅